#model-uncertainty News & Analysis

3 articles tagged with #model-uncertainty. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AINeutralarXiv – CS AI · May 97/10

🧠

Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination

Researchers have identified a geometric framework explaining how language models fail through two distinct mechanisms: parametric memory conflicting with working memory, and hallucination from absent learned facts. Both failures produce confident outputs despite being mechanistically different, but hidden-state geometry and 'geometric margin' metrics can distinguish them more reliably than traditional entropy-based detection methods.

AINeutralarXiv – CS AI · May 116/10

🧠

Offline Policy Optimization with Posterior Sampling

Researchers propose Posterior Sampling-based Policy Optimization (PSPO), a novel approach to offline reinforcement learning that addresses the critical challenge of balancing model generalization with robustness against exploitation errors. By formulating dynamics modeling as Bayesian inference, PSPO enables safer learning from out-of-distribution data while maintaining theoretical convergence guarantees.

AINeutralarXiv – CS AI · Mar 33/105

🧠

Robust Weighted Triangulation of Causal Effects Under Model Uncertainty

Researchers developed a new framework for causal effect triangulation that combines multiple statistical models to improve causal inference from observational data. The method addresses model uncertainty by using data-driven measures of model validity without requiring commitment to a single specification.